{"id":"https://openalex.org/W7162121439","doi":"https://doi.org/10.48550/arxiv.2605.22593","title":"Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?","display_name":"Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?","publication_year":2026,"publication_date":"2026-05-21","ids":{"openalex":"https://openalex.org/W7162121439","doi":"https://doi.org/10.48550/arxiv.2605.22593"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.22593","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22593","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.22593","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136785436","display_name":"Pedro C. Vieira","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vieira, Pedro C.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136765584","display_name":"Pedro Ribeiro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ribeiro, Pedro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075044662","display_name":"Viacheslav Borovitskiy","orcid":"https://orcid.org/0000-0002-3539-333X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Borovitskiy, Viacheslav","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.8500999808311462,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.8500999808311462,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.06019999831914902,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.034299999475479126,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5609999895095825},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5188000202178955},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47429999709129333},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45910000801086426},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.40450000762939453},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4041000008583069}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6367999911308289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6309000253677368},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5609999895095825},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5188000202178955},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5040000081062317},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47429999709129333},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45910000801086426},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3061999976634979},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2897000014781952},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2759000062942505},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2732999920845032}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.22593","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22593","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.22593","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22593","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"deep":[1,15,37,152],"ensembles":[2,38,57,112],"are":[3],"widely":[4],"considered":[5],"to":[6,100,159],"be":[7],"the":[8,67,107],"default":[9],"method":[10],"for":[11,19,40],"uncertainty":[12,85],"quantification":[13],"in":[14,29,77],"learning,":[16],"their":[17,121],"effectiveness":[18],"graph-structured":[20],"data":[21],"is":[22,106,132],"often":[23],"simply":[24],"assumed":[25],"based":[26],"on":[27],"successes":[28],"domains":[30],"like":[31],"computer":[32],"vision.":[33],"We":[34],"investigate":[35],"standard":[36],"specifically":[39],"message-passing":[41],"graph":[42,160],"neural":[43],"networks.":[44],"Benchmarking":[45],"across":[46],"seven":[47],"datasets":[48],"representing":[49],"varied":[50],"tasks":[51],"and":[52],"complexities,":[53],"we":[54,91,128],"reveal":[55],"that":[56,151],"provide":[58],"surprisingly":[59],"little":[60],"improvement":[61],"over":[62],"a":[63],"single":[64],"model.":[65],"Instead,":[66],"observed":[68],"marginal":[69],"gains":[70],"stem":[71],"primarily":[72],"from":[73],"stabilizing":[74],"optimization":[75],"noise":[76],"point":[78],"predictions":[79],"rather":[80,136],"than":[81,137],"yielding":[82],"meaningfully":[83],"better":[84],"estimates.":[86],"Through":[87],"an":[88],"aleatoric-epistemic":[89],"decomposition,":[90],"identify":[92],"epistemic":[93,114],"collapse:":[94],"independently":[95],"trained":[96],"networks":[97],"consistently":[98],"converge":[99],"overly":[101],"similar":[102],"predictions.":[103],"Because":[104],"disagreement":[105],"fundamental":[108],"mechanism":[109],"through":[110],"which":[111],"capture":[113],"uncertainty,":[115],"this":[116,125,130],"lack":[117],"of":[118],"diversity":[119],"neutralizes":[120],"key":[122],"advantage.":[123],"Analyzing":[124],"phenomenon":[126],"further,":[127],"suggest":[129,150],"collapse":[131],"driven":[133],"by":[134],"functional":[135],"weight-space":[138],"convexity,":[139],"where":[140],"distinct":[141],"parameter":[142],"solutions":[143],"induce":[144],"almost":[145],"identical":[146],"behavior.":[147],"Our":[148],"results":[149],"ensemble":[153],"success":[154],"does":[155],"not":[156],"seamlessly":[157],"transfer":[158],"machine":[161],"learning.":[162]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-23T00:00:00"}